Skip to content

Instantly share code, notes, and snippets.

@simonrolph

simonrolph/generate_ro_card.ipynb

Created May 9, 2023 08:31
Show Gist options
  • Save simonrolph/19d16503794239cd46cc03bb1c173614 to your computer and use it in GitHub Desktop.
Save simonrolph/19d16503794239cd46cc03bb1c173614 to your computer and use it in GitHub Desktop.
Download ZIP
generate_ro_card.ipynb
Display the source blob
Display the rendered blob
Raw
generate_ro_card.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyMeook7kl4F+aRSDFmOQpAR",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/simonrolph/19d16503794239cd46cc03bb1c173614/generate_ro_card.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"id": "bcFAmIr0W2Td"
},
"outputs": [],
"source": [
"#load required libraries\n",
"import requests\n",
"import json"
]
},
{
"cell_type": "markdown",
"source": [
"Functions that take an identifier (eg. doi) and return an 'entity' which will form part of the RO-Card. Some lines are commented ot becuase this information was provided for some entities not others so it would error."
],
"metadata": {
"id": "TzjzXpKOXAqy"
}
},
{
"cell_type": "code",
"source": [
"# GET MANUSCRIPT\n",
"def convert_crossref_to_entity(doi):\n",
" #get response\n",
" response = requests.get(f\"https://api.crossref.org/works/{doi}\")\n",
" crossref_api_response = response.json()\n",
" \n",
" # Manuscript\n",
" # Extract relevant metadata from the CrossRef API response\n",
" title = crossref_api_response['message']['title'][0]\n",
" authors = crossref_api_response['message']['author']\n",
" #abstract = crossref_api_response['message']['abstract']\n",
" container_title = crossref_api_response['message']['container-title'][0]\n",
" volume = crossref_api_response['message']['volume']\n",
" #issue = crossref_api_response['message']['issue']\n",
" #page = crossref_api_response['message']['page']\n",
" date_parts = crossref_api_response['message']['issued']['date-parts'][0]\n",
" year = date_parts[0]\n",
" month = date_parts[1]\n",
" #day = date_parts[2] \n",
"\n",
" # Construct the RO-Crate JSON structure\n",
" ro_crate_json = {\n",
" \"@id\": f\"https://doi.org/{doi}\",\n",
" \"@type\": \"ScholarlyArticle\",\n",
" \"identifier\": doi,\n",
" \"name\": title,\n",
" \"datePublished\": f\"{year}-{month:02d}\",\n",
" \"author\": [{\"@type\": \"Person\", \"name\": f\"{author['given']} {author['family']}\"} for author in authors],\n",
" #\"description\": abstract,\n",
" \"isPartOf\": {\"@id\": container_title, \"volumeNumber\": volume}\n",
" }\n",
"\n",
" # Return the ro entity json\n",
" return ro_crate_json\n",
"\n",
"# example\n",
"# Retrieve the CrossRef API response for the DOI \"10.1371/journal.pbio.3001991\"\n",
"# doi = \"10.1371/journal.pbio.3001991\"\n",
"# ro_crate_article = convert_crossref_to_entity(doi)\n",
"# ro_crate_article"
],
"metadata": {
"id": "rNfBvHaEW8dD"
},
"execution_count": 7,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# GET SOFTWARE FROM ZENODO\n",
"def generate_software_ro_crate_zenodo(zenodo_repo_id):\n",
" \n",
" # Define the Zenodo API endpoint URLs\n",
" base_url = \"https://zenodo.org/api/\"\n",
" deposition_url = base_url + \"deposit/depositions\"\n",
" software_url = base_url + f\"records/{zenodo_repo_id}\"\n",
" \n",
" # Retrieve the software metadata from Zenodo\n",
" software_response = requests.get(software_url)\n",
" software_metadata = software_response.json()\n",
" \n",
" # Extract relevant metadata from the software metadata\n",
" title = software_metadata['metadata']['title']\n",
" description = software_metadata['metadata']['description']\n",
" authors = software_metadata['metadata']['creators']\n",
" date = software_metadata['metadata']['publication_date']\n",
" version = software_metadata['metadata']['version']\n",
" license = software_metadata['metadata']['license']['id']\n",
" keywords = software_metadata['metadata'].get('keywords', [])\n",
"\n",
" # Create the RO-Crate JSON structure\n",
" ro_crate_json = {\n",
" \"@id\": f\"https://zenodo.org/record/{zenodo_repo_id}\",\n",
" \"@type\": \"Software\",\n",
" \"identifier\": zenodo_repo_id,\n",
" \"name\": title,\n",
" \"version\": version,\n",
" \"description\": description,\n",
" \"datePublished\": date,\n",
" \"author\": [{\"@type\": \"Person\", \"name\": f\"{author['name']}\"} for author in authors],\n",
" \"keywords\": keywords,\n",
" \"license\": {\"@id\": f\"https://spdx.org/licenses/{license}.html\"}\n",
" }\n",
"\n",
" # Return the filename of the generated RO-Crate JSON file\n",
" return ro_crate_json\n",
"\n",
"# example\n",
"# zenodo_repo_id = 7886834\n",
"# ro_crate_software_zenodo = generate_software_ro_crate(zenodo_repo_id)\n",
"# ro_crate_software_zenodo"
],
"metadata": {
"id": "-rKtT4gAXL0B"
},
"execution_count": 8,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# GET SOFTWARE FROM GITHUB\n",
"def generate_software_ro_crate_github(github_repo_owner, github_repo_name): \n",
" # Define the GitHub API endpoint URLs\n",
" base_url = \"https://api.github.com/\"\n",
" repo_url = base_url + f\"repos/{github_repo_owner}/{github_repo_name}\"\n",
" \n",
" # Retrieve the software metadata from GitHub\n",
" repo_response = requests.get(repo_url)\n",
" repo_metadata = repo_response.json()\n",
" \n",
" # Extract relevant metadata from the repo metadata\n",
" title = repo_metadata['name']\n",
" description = repo_metadata['description']\n",
" #authors = [{\"name\": contributor['login']} for contributor in repo_metadata['contributors']]\n",
" date = repo_metadata['created_at']\n",
" version = repo_metadata['default_branch']\n",
" license_url = repo_metadata['license']['url']\n",
" license_response = requests.get(license_url)\n",
" license_metadata = license_response.json()\n",
" license = license_metadata['spdx_id']\n",
" keywords = repo_metadata.get('topics', [])\n",
"\n",
" # Create the RO-Crate JSON structure\n",
" ro_crate_json = {\n",
" \"@id\": f\"https://github.com/{github_repo_owner}/{github_repo_name}\",\n",
" \"@type\": \"Software\",\n",
" \"identifier\": f\"{github_repo_owner}/{github_repo_name}\",\n",
" \"name\": title,\n",
" \"version\": version,\n",
" \"description\": description,\n",
" \"datePublished\": date,\n",
" #\"author\": [{\"@type\": \"Person\", \"name\": f\"{author['name']}\"} for author in authors],\n",
" \"keywords\": keywords,\n",
" \"license\": {\"@id\": f\"https://spdx.org/licenses/{license}.html\"}\n",
" }\n",
"\n",
" # Return the generated RO-Crate JSON file\n",
" return ro_crate_json\n",
"\n",
"# example\n",
"# github_repo_owner = \"trixi-framework\"\n",
"# github_repo_name = \"Trixi.jl\"\n",
"# ro_crate_software_github = generate_software_ro_crate(github_repo_owner, github_repo_name)\n",
"# ro_crate_software_github"
],
"metadata": {
"id": "tkRt5vtCXQgZ"
},
"execution_count": 9,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Then we can call each of the functions and put it together into an RO-Card. It prints it."
],
"metadata": {
"id": "Z79clFxIXRGp"
}
},
{
"cell_type": "code",
"source": [
"# get entities\n",
"\n",
"#article\n",
"doi = \"10.1016/j.jcp.2021.110467\"\n",
"ro_crate_article = convert_crossref_to_entity(doi)\n",
"\n",
"#software zendodo\n",
"zenodo_repo_id = 7886834\n",
"ro_crate_software_zenodo = generate_software_ro_crate_zenodo(zenodo_repo_id)\n",
"\n",
"#software github\n",
"github_repo_owner = \"trixi-framework\"\n",
"github_repo_name = \"Trixi.jl\"\n",
"ro_crate_software_github = generate_software_ro_crate_github(github_repo_owner, github_repo_name)\n",
"\n",
"# RO-Card details\n",
"ro_card_name = \"Trixi Framework\"\n",
"ro_card_description = \"This is the description\"\n",
"\n",
"\n",
"# Build RO card from entities\n",
"ro_card = { \n",
" \"@context\": \"https://w3id.org/ro/crate/1.1/context\", \n",
" \"@graph\": [\n",
" {\n",
" \"@type\": \"CreativeWork\",\n",
" \"@id\": \"ro-crate-metadata.json\",\n",
" \"conformsTo\": {\"@id\": \"https://w3id.org/ro/crate/1.1\"},\n",
" \"about\": {\"@id\": \"./\"}\n",
" },\n",
" {\n",
" \"@id\": \"./\",\n",
" \"@type\": \"Dataset\",\n",
" \"name\" : ro_card_name,\n",
" \"description\" : ro_card_description, \n",
" },\n",
" \n",
" ro_crate_article,\n",
" ro_crate_software_zenodo,\n",
" ro_crate_software_github\n",
" \n",
" ]\n",
"}\n",
"print(json.dumps(ro_card, indent=2))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "p72XDguSYjzt",
"outputId": "dae7b84e-e952-487f-9363-f1a33922ede7"
},
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"{\n",
" \"@context\": \"https://w3id.org/ro/crate/1.1/context\",\n",
" \"@graph\": [\n",
" {\n",
" \"@type\": \"CreativeWork\",\n",
" \"@id\": \"ro-crate-metadata.json\",\n",
" \"conformsTo\": {\n",
" \"@id\": \"https://w3id.org/ro/crate/1.1\"\n",
" },\n",
" \"about\": {\n",
" \"@id\": \"./\"\n",
" }\n",
" },\n",
" {\n",
" \"@id\": \"./\",\n",
" \"@type\": \"Dataset\",\n",
" \"name\": \"Trixi Framework\",\n",
" \"description\": \"This is the description\"\n",
" },\n",
" {\n",
" \"@id\": \"https://doi.org/10.1016/j.jcp.2021.110467\",\n",
" \"@type\": \"ScholarlyArticle\",\n",
" \"identifier\": \"10.1016/j.jcp.2021.110467\",\n",
" \"name\": \"A purely hyperbolic discontinuous Galerkin approach for self-gravitating gas dynamics\",\n",
" \"datePublished\": \"2021-10\",\n",
" \"author\": [\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Michael Schlottke-Lakemper\"\n",
" },\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Andrew R. Winters\"\n",
" },\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Hendrik Ranocha\"\n",
" },\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Gregor J. Gassner\"\n",
" }\n",
" ],\n",
" \"isPartOf\": {\n",
" \"@id\": \"Journal of Computational Physics\",\n",
" \"volumeNumber\": \"442\"\n",
" }\n",
" },\n",
" {\n",
" \"@id\": \"https://zenodo.org/record/7886834\",\n",
" \"@type\": \"Software\",\n",
" \"identifier\": 7886834,\n",
" \"name\": \"Trixi.jl\",\n",
" \"version\": \"v0.5.19\",\n",
" \"description\": \"Adaptive high-order numerical simulations of hyperbolic PDEs in Julia\",\n",
" \"datePublished\": \"2023-05-02\",\n",
" \"author\": [\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Schlottke-Lakemper, Michael\"\n",
" },\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Gassner, Gregor J.\"\n",
" },\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Ranocha, Hendrik\"\n",
" },\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Winters, Andrew R.\"\n",
" },\n",
" {\n",
" \"@type\": \"Person\",\n",
" \"name\": \"Chan, Jesse\"\n",
" }\n",
" ],\n",
" \"keywords\": [],\n",
" \"license\": {\n",
" \"@id\": \"https://spdx.org/licenses/MIT.html\"\n",
" }\n",
" },\n",
" {\n",
" \"@id\": \"https://github.com/trixi-framework/Trixi.jl\",\n",
" \"@type\": \"Software\",\n",
" \"identifier\": \"trixi-framework/Trixi.jl\",\n",
" \"name\": \"Trixi.jl\",\n",
" \"version\": \"main\",\n",
" \"description\": \"Trixi.jl: Adaptive high-order numerical simulations of hyperbolic PDEs in Julia\",\n",
" \"datePublished\": \"2020-08-18T06:42:03Z\",\n",
" \"keywords\": [\n",
" \"adaptive-mesh-refinement\",\n",
" \"amr\",\n",
" \"conservation-laws\",\n",
" \"discontinuous-galerkin\",\n",
" \"julia\",\n",
" \"numerical-simulation-framework\",\n",
" \"simulation\",\n",
" \"summation-by-parts\"\n",
" ],\n",
" \"license\": {\n",
" \"@id\": \"https://spdx.org/licenses/MIT.html\"\n",
" }\n",
" }\n",
" ]\n",
"}\n"
]
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment